• Nuclear Engineering and Technology
• /
• 제52권9호
• /
• pp.1998-2008
• /
• 2020

Solenoid operated valves (SOV) play important roles in industrial process to control the flow of fluids. Solenoid valves can be found in so many industries as well as the nuclear plant. The ability to be able to detect the presence of faults and predicting the remaining useful life (RUL) of the SOV is important in maintenance planning and also prevent unexpected interruptions in the flow of process fluids. This paper proposes a fault diagnosis method for the alternating current (AC) powered SOV. Previous research work have been focused on direct current (DC) powered SOV where the current waveform or vibrations are monitored. There are many features hidden in the AC waveform that require further signal analysis. The analysis of the AC powered SOV waveform was done in the time and frequency domain. A total of sixteen features were obtained and these were used to classify the different operating modes of the SOV by applying a machine learning technique for classification. Also, a deep neural network (DNN) was developed for the prediction of RUL based on the failure modes of the SOV. The results of this paper can be used to improve on the condition based monitoring of the SOV.

• 부모자녀건강학회지
• /
• 제11권1호
• /
• pp.61-72
• /
• 2008

This study is a descriptive research attempted to examine the exercise practice of junior high school students and figure out their changing process, decision-making balance, and self-efficacy according to the exercise practice so that they can be utilized as fundamental data for developing exercise intervention programs for junior high school students. The study subjects were students from five junior high schools in B City. Total 600 questionnaires were distributed, and 554 responded ones were analyzed. The collected data were analyzed using SPSS/Win 10.0. According to the results of analyzing the subjects with the exercise changing stage tool, exercise non-practice group including the precontemplation stage, contemplation stage, and preparation stage occupies 57.6% while the exercise practice group including the action stage and maintenance stage consists of 42.4%. And according to the results of discriminating analysis setting total 10 factors of transtheoretical model variables as predictive factors to predict each group based on whether they practice exercise or not, it was found out that the subordinate factors of the changing process, consciousness-raising (F=33.98, p=.000), self-cognitive decision (F=21.55, p=.000), contrary condition provision (F=84.67, p=.000), helping relationship (F=28.52, p=.000), reinforced thinking (F=14.15, p=.000), and stimulus control (F=54.64, p=.000), and the subordinate factors of the decision-making balance, beneficial factors (F=15.65, p= .000) and hindering factors (F=8.58, p=.004), and self-efficacy (F=78.60. p=.000) were significant predictive factors and discriminating variables. Based on the research findings above, it will be necessary to develop exercise intervention programs sufficiently reflecting the changing process, decision-making balance, and self-efficacy suitably for the subjects and make strategies to encourage their active participation and exercise maintenance, through verifying transtheoretical model variables according to whether the junior high school students practice exercise or not.

• 정보과학회 논문지
• /
• 제42권7호
• /
• pp.840-845
• /
• 2015

최근 빅데이터는 전사적 자원관리 분야뿐만 아니라 해양플랜트내 생산 및 운영 작업 분야에서도 큰 관심을 받고 있다. 이력데이터를 기반으로 미래의 설비에 대한 성능을 예측하는 것은 설비들의 생산성을 향상 시킬 수 있다. 특히 해양플랜트의 주요설비 중 하나인 원심압축기는 고장 시 폭발 할 수 있는 위험한 설비이기 때문에 실시간으로 설비성능을 모니터링 해야 한다. 본 논문에서 원심압축기의 성능을 계산하기 위한 스트림 데이터 처리 구조를 제안한다. 제안하는 시스템은 크게 가상태그 스트림 생성기와 실시간 데이터 스트림 관리자와 같이 두 가지 컴포넌트로 구성된다. 시스템 성능 확장성을 제공하기 위해, 멀티 코어 CPU를 사용하여 대용량 스트림 데이터를 처리할 수 있는 병렬 프로그래밍 접근 방식을 이용하였다. 또한, 실험을 통해 원심압축기의 스트림 데이터 처리에 대한 성능 개선을 보여주었다.

• 한국학교ㆍ지역보건교육학회지
• /
• 제18권2호
• /
• pp.55-70
• /
• 2017

Objectives: The purpose of this study was to identify the factors associated with stage of change for drinking cessation among adolescents on the basis of the Transtheoretical Model. Methods: The data was collected from 343 high school students in Kimhae-city, who have experienced any kind of alcohol in their lifetime. For data analysis, descriptive statistics and Logistic regression were performed using the SPSS WIN 18. 0 program. Results: The stage of change was as follows: 24.2% in the precontemplation stage, 8.7% in the contemplation stage, 10.8% in the preparation stage, 39.7% in the action stage and 16.6% in maintenance stage. The predictive factors to move from the precontemplation stage to the contemplation/preparation stage were dramatic relief (OR=1.36, 95% CI:1.13-1.63) and self-efficacy (OR=1.05, 95% CI:1.01-1.09). The predictive factors to move from the contemplation/preparation stage to the action/maintenance stage were female (OR=0.50, 95% CI:0.27-0.94), the number of friend who have drunk (OR=0.84, 95% CI:0.77-0.91) and self-efficacy (OR=1.04, 95% CI: 1.00-1.07). Conclusions: To stop adolescent drinking, this study suggests the intervention program needs to be considered the individual's stage of change of drinking. The intervention program to enhance dramatic relief and self-efficacy is needed to adolescents in the precontemplation stage. It is crucial to develop strategies to raise self-efficacy for adolescents in the contemplation/preparation stage, which also respect their gender and peer groups.

• 대한토목학회논문집
• /
• 제43권3호
• /
• pp.397-411
• /
• 2023

국내에서 공용연수 30년 이상인 노후 교량의 수가 급증하고 있다. 이에 따라 교량 노후도, 상태 및 성능 예측을 바탕으로 한 첨단 유지관리 기술의 중요성이 점차 주목받고 있다. 이 연구에서는 머신러닝 기반의 의사결정나무 및 랜덤포레스트 분류 모델을 사용하여 교량의 안전등급을 예측하는 방법을 제안하였다. 일반국도상 교량 8,850개를 대상으로 해당 모델들을 혼동행렬, 균형 정확도, 재현율, ROC 곡선 및 AUC와 같이 여러가지 평가 지표를 통해 분석한 결과 전반적으로 랜덤포레스트가 의사결정나무보다 더 나은 예측 성능을 보유하였다. 특히 랜덤포레스트 중 랜덤 언더 샘플링 기법은 노후도가 비교적 커서 유지관리에 주의를 기울여야 하는 C, D등급 교량에 대해 재현율 83.4%로 다른 샘플링 기법들보다 예측 성능이 더 뛰어난 것으로 나타났다. 제안된 모델은 최근 점검이 실시되지 않은 교량들의 신속한 안전등급 파악 및 효율적이고 경제적인 유지관리 계획 수립에 유용하게 활용될 수 있을 것으로 기대된다.

• 산업경영시스템학회지
• /
• 제40권1호
• /
• pp.57-64
• /
• 2017

In order to reduce damages to major railroad components, which have the potential to cause interruptions to railroad services and safety accidents and to generate unnecessary maintenance costs, the development of rolling stock maintenance technology is switching from preventive maintenance based on the inspection period to predictive maintenance technology, led by advanced countries. Furthermore, to enhance trust in accordance with the speedup of system and reduce maintenances cost simultaneously, the demand for fault diagnosis and prognostic health management technology is increasing. The objective of this paper is to propose a highly reliable learning model using various machine learning algorithms that can be applied to critical rolling stock components. This paper presents a model for railway rolling stock component fault diagnosis and conducts a mechanical failure diagnosis of motor components by applying the machine learning technique in order to ensure efficient maintenance support along with a data preprocessing plan for component fault diagnosis. This paper first defines a failure diagnosis model for rolling stock components. Function-based algorithms ANFIS and SMO were used as machine learning techniques for generating the failure diagnosis model. Two tree-based algorithms, RadomForest and CART, were also employed. In order to evaluate the performance of the algorithms to be used for diagnosing failures in motors as a critical railroad component, an experiment was carried out on 2 data sets with different classes (includes 6 classes and 3 class levels). According to the results of the experiment, the random forest algorithm, a tree-based machine learning technique, showed the best performance.

• Journal of Platform Technology
• /
• 제6권3호
• /
• pp.47-54
• /
• 2018

하드웨어 산업에서의 예측 분석은 생산설비의 고장을 방지하기 위해 적절한 시점에 유지보수를 수행할 수 있고 관리비용을 절감할 수 있다. 이는 고장원인분석의 자동화를 통해 보다 효율적이고 과학적인 유지보수를 수행할 수 있도록 도와준다. 그중에서도 예측 관리는 정보 기술을 활용하여 설비 상태의 수집, 분석, 과학적 데이터 관리를 통해 예측 모델을 구성하며, 이를 바탕으로 이상상태를 파악하고 개선함으로써 이상상태가 발생하는 것을 사전에 예방하는 것을 목적으로 한다. 본 연구에서는 Relex 도구를 통해 결함트리(Fault Tree)를 만들고 하드웨어들의 에러코드를 분석하여 안전성을 연구했다.

• 수산해양기술연구
• /
• 제56권4호
• /
• pp.384-394
• /
• 2020

This paper proposes an outlier detection model based on machine learning that can diagnose the presence or absence of major engine parts through unsupervised learning analysis of main engine big data of a ship. Engine big data of the ship was collected for more than seven months, and expert knowledge and correlation analysis were performed to select features that are closely related to the operation of the main engine. For unsupervised learning analysis, ensemble model wherein many predictive models are strategically combined to increase the model performance, is used for anomaly detection. As a result, the proposed model successfully detected the anomalous engine status from the normal status. To validate our approach, clustering analysis was conducted to find out the different patterns of anomalies the anomalous point. By examining distribution of each cluster, we could successfully find the patterns of anomalies.

• 대한간호학회지
• /
• 제35권7호
• /
• pp.1285-1294
• /
• 2005

Purpose: This study was done to evaluate the predictive value of aspects of the Transtheoretical model (TTM) of behavior change as applied to smoking cessation in a rural population. Method: A convenience sample was recruited from a public health center in a community. A total of 484 participants were recruited, including 319 smokers, 116 ex-smokers and 49 non-smokers. A cross-sectional and descriptive design was used in this study. Data was analyzed using descriptive statistics, frequency statistics, ANOVA and Logistic regression. Result: The major findings were 1) The participants were assessed at baseline for their current Stage of Change resulting in a distribution with $42.1\%$ in Precontemplation, $24.1\%$ in Contemplation, $9.7\%$ in Preparation, $6.2\%$ in Active, and $17.9\%$ in the Maintenance stage. 2) There were statistically significant differences of processes of change, decisional balance and situational temptation across the stages of change. 3) The main factors that affect smoking cessation were age, number of years smoking, age when began smoking, self-liberation and negative/affective situations, which combined explained $33.2\%$ of the smoking cessation. Conclusion: TTM variables measured prior to a smoking cessation program added little predictive value for cessation outcome beyond that explained by demographic and smoking history variables.

• 터널과지하공간
• /
• 제29권5호
• /
• pp.356-366
• /
• 2019

다양한 TBM 성능 예측 모델이 개발되었기만 대부분 관입율 예측에 한정되어 있다. 일부 모델들이 수식과 그래프를 이용하여 TBM 가동율을 추정하는 방법을 제시하기도 하지만, TBM 가동율에 대한 연구는 매우 드문 편이다. TBM 가동율은 TBM 장비의 종류, 운영, 유지보수, 지질 조건, 시공자의 경험 등에 영향을 받는다. 본 연구에서는 100여개 이상의 사례 분석을 통해서 TBM 가동율과 RMR, 암종 등의 지반 조건, TBM의 종류, 터널의 연장 및 직경 등과의 관계를 조사하였다. 단순 및 다중 회귀분석을 수행하여 TBM 가동율 예측모델을 개발하였다. 암종 등의 지반조건, TBM의 종류, 터널의 연장 및 직경 등을 설명 변수로 갖는 회귀모델은 낮은 상관계수를 나타내었다. RMR을 설명변수로 갖는 회귀모델이 더 높은 상관계수를 나타내었다.